© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28122
    Prev
    Next
    INDEX
    Explanations

    references to archival resources or records related to history

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingu
    -0.07
    imas
    -0.07
    .Reporting
    -0.07
    ÇIJ
    -0.07
    elog
    -0.07
     æ¨
    -0.07
    GH
    -0.07
    олом
    -0.07
    ovol
    -0.07
    .Apis
    -0.07
    POSITIVE LOGITS
     Mess
    0.06
     primary
    0.06
    ernel
    0.06
     Esp
    0.06
     Grove
    0.06
     sworn
    0.06
    Ģ
    0.06
     UINavigationController
    0.05
    ust
    0.05
    primary
    0.05
    Activations Density 0.000%

    No Known Activations